Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4784 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.9919. Min Act: -0.1700
Data Index: 6487208 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.8356. Min Act: -0.1700
Data Index: 6057740 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.8356. Min Act: -0.1700
Data Index: 6430242 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3981. Min Act: -0.1700
Data Index: 7449619 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.4294. Min Act: -0.1700
Data Index: 5355662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.4294. Min Act: -0.1700
Data Index: 8222569 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.4294. Min Act: -0.1700
Data Index: 3585543 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3981. Min Act: -0.1700
Data Index: 5494266 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3981. Min Act: -0.1700
Data Index: 1319820 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3981. Min Act: -0.1700
Data Index: 8035058 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3669. Min Act: -0.1700
Data Index: 6932588 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3669. Min Act: -0.1700
Data Index: 5031664 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3356. Min Act: -0.1700
Data Index: 3430910 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3356. Min Act: -0.1700
Data Index: 6100114 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3669. Min Act: -0.1700
Data Index: 8041657 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3044. Min Act: -0.1700
Data Index: 6083161 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3044. Min Act: -0.1700
Data Index: 4240184 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.2731. Min Act: -0.1700
Data Index: 1815407 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.3044. Min Act: -0.1700
Data Index: 1812266 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9919. Min Range: -6.9919
Max Act: 6.2731. Min Act: -0.1700
Data Index: 5649792 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19